← Back to Skills Marketplace
mr-11even

Podcastfy Openclaw Skill

by mr-11even · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
146
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install podcastfy-openclaw-skill
Description
Convert text, images, PDFs, websites, or YouTube videos into multilingual AI-generated podcast audio using Podcastfy's open-source Python toolkit.
Usage Guidance
This skill appears coherent with its purpose, but before installing or using it: 1) Verify the podcastfy PyPI package and GitHub repo (check maintainer, recent commits, issues) to reduce supply-chain risk. 2) Store API keys (Gemini/OpenAI/ElevenLabs) in a secure place and use least-privilege/separate keys; do not put them in shared folders or source control. 3) Be aware that content you provide (URLs, PDFs, video audio, images, patient/medical content) may be transmitted to third‑party LLM/TTS services — avoid uploading sensitive or PHI unless you have appropriate agreements and controls. 4) Run installs and the tool in an isolated environment (virtualenv, container) if you want to limit system impact. 5) Confirm how YouTube downloading/transcription is implemented (additional dependencies or network access may be required). 6) If privacy is a priority, test the --local option and audit what 'local' actually uses. If you want more assurance, review the repository source or run the package in a sandbox before supplying production or sensitive content.
Capability Assessment
Purpose & Capability
Name/description claim converting multi-modal content to podcast audio using Podcastfy; SKILL.md only asks for installing the podcastfy PyPI package, FFmpeg, and API keys for LLM/TTS providers (OpenAI, Gemini, ElevenLabs) which are appropriate and expected for that functionality.
Instruction Scope
Instructions are limited to installing podcastfy/FFmpeg, creating a .env with LLM/TTS keys, and running podcastfy CLI or Python API on user-provided URLs/files. This correctly implies sending content to external LLM/TTS services; users should note that content and transcripts will be transmitted to whichever APIs are configured. The doc doesn't explicitly list any auxiliary downloader dependency (e.g., youtube-dl/pytube) though YouTube support is documented — this is likely handled by the package but worth confirming.
Install Mechanism
The registry entry is instruction-only (no install spec). SKILL.md recommends pip install podcastfy and installing FFmpeg via apt/brew — both are standard. Because installation happens at the user's side via pip, users should verify the PyPI package and repository before installing.
Credentials
The skill asks for API keys for LLM and TTS providers (GEMINI_API_KEY, OPENAI_API_KEY, optional ELEVENLABS_API_KEY). Those are directly relevant to generating transcripts and TTS; no unrelated credentials, config paths, or excessive env access are requested.
Persistence & Privilege
always is false and the skill is user-invocable only. The skill does not request persistent/always-on privileges or access to other skills' configs; it merely instructs running the Podcastfy CLI or Python API at runtime.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install podcastfy-openclaw-skill
  3. After installation, invoke the skill by name or use /podcastfy-openclaw-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Podcastfy Skill for OpenClaw 1.0.0 initial release: - Introduces integration with the open-source Podcastfy tool for generating AI-powered podcasts from multi-modal content (text, images, PDFs, websites, YouTube). - Provides step-by-step installation instructions, API key setup, and supported TTS models. - Offers detailed CLI and Python API usage examples, including advanced options. - Includes practical guides for dental/medical use cases and integration with OpenClaw workflows. - Lists troubleshooting tips and direct links to resources for further support.
Metadata
Slug podcastfy-openclaw-skill
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Podcastfy Openclaw Skill?

Convert text, images, PDFs, websites, or YouTube videos into multilingual AI-generated podcast audio using Podcastfy's open-source Python toolkit. It is an AI Agent Skill for Claude Code / OpenClaw, with 146 downloads so far.

How do I install Podcastfy Openclaw Skill?

Run "/install podcastfy-openclaw-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Podcastfy Openclaw Skill free?

Yes, Podcastfy Openclaw Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Podcastfy Openclaw Skill support?

Podcastfy Openclaw Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Podcastfy Openclaw Skill?

It is built and maintained by mr-11even (@mr-11even); the current version is v1.0.0.

💬 Comments